© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10867
    Prev
    Next
    INDEX
    Explanations

    rain or rainy weather

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anc
    -0.10
     bra
    -0.10
    è¿ĻåĿĹ
    -0.09
    ALER
    -0.09
     Prescott
    -0.09
    ROID
    -0.09
     Nunes
    -0.09
    é«®
    -0.09
    æ¤į
    -0.09
    åĸī
    -0.09
    POSITIVE LOGITS
    æ¶ķ
    0.10
    åİŁåĽłä¹ĭä¸Ģ
    0.10
    æ·ĭ
    0.09
    âĺĶ
    0.09
    forest
    0.09
    à¸ĩ
    0.09
    åĩij
    0.09
    EDI
    0.08
    obb
    0.08
    æĸĹ
    0.08
    Activations Density 0.017%

    No Known Activations